Class: FastaReader

Inherits:
Object
  • Object
show all
Defined in:
lib/bio-table/parsers/fastareader.rb

Instance Method Summary collapse

Constructor Details

#initialize(fn, regex = nil) ⇒ FastaReader

Initalize the reader of FASTA file fn. Options can be :regex and :index (true/false)



19
20
21
22
23
24
25
26
27
# File 'lib/bio-table/parsers/fastareader.rb', line 19

def initialize fn, regex = nil
  @logger = Bio::Log::LoggerPlus['bio-table']
  @f = File.open(fn)
  @fread_once = false
  @regex = regex
  @regex = '^(\S+)' if @regex == nil
  @regex = '('+regex+')' if regex !~ /\(/
  @logger.info "Parsing FASTA with ID regex '"+@regex+"'"
end

Instance Method Details

#closeObject



126
127
128
# File 'lib/bio-table/parsers/fastareader.rb', line 126

def close
  @f.close
end

#digest_tag(tag) ⇒ Object



106
107
108
109
110
111
112
113
114
115
116
117
118
# File 'lib/bio-table/parsers/fastareader.rb', line 106

def digest_tag tag
  if tag =~ /^>/
    descr = $'.strip
    matches = /#{@regex}/.match(descr).captures
    if matches.size > 0
      # p matches
      return matches.join("\t"), descr
    end
    p descr  # do not remove these
    p @regex
  end
  raise "Can not digest '#{tag}' using '"+@regex+"'"
end

#eachObject

returns a FastaRecord for every item (invokes parse_each)



64
65
66
# File 'lib/bio-table/parsers/fastareader.rb', line 64

def each
  parse_each { | id, descr, seq | yield FastaRecord.new(id, descr, seq) }
end

#firstObject



68
69
70
71
72
# File 'lib/bio-table/parsers/fastareader.rb', line 68

def first
  parse_each { | id, descr, seq | 
    return FastaRecord.new(id, descr, seq) 
  }
end

#get(id) ⇒ Object

Return a record by its id, nil when not found



75
76
77
78
79
80
81
82
# File 'lib/bio-table/parsers/fastareader.rb', line 75

def get id
  indexed?
  if fpos = indexer_get(id)
    get_rec(fpos)
  else
    nil
  end
end

#get_by_index(idx) ⇒ Object



97
98
99
100
101
102
103
104
# File 'lib/bio-table/parsers/fastareader.rb', line 97

def get_by_index idx
  indexed?
  if fpos = indexer_get_by_index(idx)[1]
    ret = get_rec(fpos)
    return ret
  end
  nil
end

#get_rec(fpos) ⇒ Object



84
85
86
87
88
89
90
91
92
93
94
95
# File 'lib/bio-table/parsers/fastareader.rb', line 84

def get_rec fpos
  @f.seek fpos
  tag = @f.gets
  seq = ""
  begin
    line = @f.gets
    break if line =~ /^>/
    seq += line.strip 
  end while !@f.eof
  id, descr = digest_tag(tag)
  FastaRecord.new(id,descr,seq)
end

#parse_eachObject

Parse the FASTA file and yield id, descr, sequence. When the indexer is on it will index the records the first time. Note that, with indexing, when you don’t complete parsing there will be an error the second time. This is a # trade-off, otherwise one would always have to index the file and read it twice.



34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
# File 'lib/bio-table/parsers/fastareader.rb', line 34

def parse_each
  @f.seek 0    # force file rewind
  @rec_fpos = 0
  @rec_line = @f.gets
  fpos = 0
  @count = 0
  begin
    # digest id from record description
    id, descr = digest_tag(@rec_line)
    id_fpos = @rec_fpos
    # parse the sequence
    seq = ""
    begin
      fpos = @f.tell
      line = @f.gets
      break if line =~ /^>/
      seq += line.strip 
    end while !@f.eof 
    # new record
    @count += 1
    @rec_fpos = fpos
    @rec_line = line
    # p [@rec_line, id, id_fpos]
    # indexer_set(id, id_fpos) if @indexer and not @fread_once
    yield id, descr, seq
  end while !@f.eof
  @fread_once = true
end

#sizeObject

Returns the size of the dataset - as read. After the final record the size represents the number of items in the FASTA file



122
123
124
# File 'lib/bio-table/parsers/fastareader.rb', line 122

def size
  @count
end